© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 161682
    Prev
    Next
    INDEX
    Explanations

    Scientific citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arrant
    -0.28
    ukt
    -0.26
     pitched
    -0.26
     molecules
    -0.25
     echoed
    -0.25
     pitch
    -0.24
     turn
    -0.24
    ãĤ¹ãĥ¼ãĥij
    -0.24
     knowledge
    -0.23
    æķ´åĢĭ
    -0.23
    POSITIVE LOGITS
    icians
    0.29
    èĥĮåĮħ
    0.26
    лок
    0.26
    æľīä»·åĢ¼
    0.26
    ToRemove
    0.25
    å´©æºĥ
    0.25
    麦
    0.25
    éŀħ
    0.24
    大çIJĨçŁ³
    0.24
     Attention
    0.24
    Activations Density 0.017%

    No Known Activations